Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation

Abstract

Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates on learning shared feature representation by minimizing the distribution discrepancy across different domains. Due to the fact that all the domain alignment approaches can only reduce, but not remove the domain shift. Target domain samples distributed near the edge of the clusters, or far from their corresponding class centers are easily to be misclassified by the hyperplane learned from the source domain. To alleviate this issue, we propose to joint domain alignment and discriminative feature learning, which could benefit both domain alignment and final classification. Specifically, an instance-based discriminative feature learning method and a center-based discriminative feature learning method are proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Extensive experiments show that learning the discriminative features in the shared feature space can significantly boost the performance of deep domain adaptation methods.

This paper has been accepted by AAAI-2019

References in corpus (10)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Domain Separation Networks
• Beyond Sharing Weights for Deep Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning

Cited by in corpus (6)

• Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
• Modified Distribution Alignment for Domain Adaptation with Pre-trained Inception ResNet
• Joint Semantic Domain Alignment and Target Classifier Learning for Unsupervised Domain Adaptation
• Towards Self-similarity Consistency and Feature Discrimination for Unsupervised Domain Adaptation
• Impact of ImageNet Model Selection on Domain Adaptation
• Class Distribution Alignment for Adversarial Domain Adaptation